Monthly US energy consumption (renewables)

us_renew <- read_csv(here("data","renewables_cons_prod.csv")) %>% 
  clean_names()
renew_clean <- us_renew %>% 
  mutate(description = str_to_lower(description)) %>% 
  filter(str_detect(description, pattern = "consumption")) %>% 
  filter(!str_detect(description, pattern = "total"))    #using ! gets rid of it

Convert ‘yyyymm’ column to a date

renew_date <- renew_clean %>% 
  mutate(yr_mo_day = lubridate::parse_date_time(yyyymm, "ym")) %>% #will get NAs for month = 13
  mutate(month_sep = tsibble::yearmonth(yr_mo_day)) %>% 
  mutate(value = as.numeric(value)) %>% 
  drop_na(month_sep, value)

#Make a version where I have the month and year in separate columns

renew_parsed <- renew_date %>% 
  mutate(month = month(yr_mo_day, label = TRUE)) %>% #this function just takes out the month
  mutate(year = year(yr_mo_day))

Look at it:

renew_gg <- ggplot(renew_date, aes(x = month_sep, 
                                   y = value,
                                   group = description)) + 
  geom_line(aes(color=description))

renew_gg

#this is a discreet palette, need enough colors in the package that you want

Updating my colors with paletteer palettes:

renew_gg + 
  scale_color_paletteer_d("palettetown::seadra")

Coerce renew_parsed to a tsibble

renew_ts <- as_tsibble(renew_parsed, key = description, index = month_sep)

Let’s look at our time-series data in a couple different ways

renew_ts %>% autoplot(value)

renew_ts %>% gg_subseries(value) #breaks up each source by month across different years 

#renew_ts %>% gg_season(value) #this doesn't work, but you can make in ggplot


ggplot(data = renew_parsed, aes(x = month, y = value, group = year))+
  geom_line(aes(color = year))+
  facet_wrap(~description,
             ncol = 1,
             scales = "free",
             strip.position = "right") #description names on the side

Just look at the hydroelectric energy consumption

hydro_ts <- renew_ts %>% 
  filter(description == "hydroelectric power consumption")


hydro_ts %>% autoplot(value)

hydro_ts %>% gg_subseries(value)

ggplot(data = hydro_ts, aes(x = month, y = value, group = year))+
  geom_line(aes(color = year))+
  facet_wrap(~description,
             ncol = 1,
             scales = "free",
             strip.position = "right")

What if I want quarterly average consumption for hydro?

hydro_quarterly <- hydro_ts %>% 
  index_by(year_qu = ~(yearquarter(.))) %>% #index over a particular increment of time
  summarize(avg_consumption = mean(value))

head(hydro_quarterly)
## # A tsibble: 6 x 2 [1Q]
##   year_qu avg_consumption
##     <qtr>           <dbl>
## 1 1973 Q1            261.
## 2 1973 Q2            255.
## 3 1973 Q3            212.
## 4 1973 Q4            225.
## 5 1974 Q1            292.
## 6 1974 Q2            290.

Decompose that hydro_ts time series data

dcmp <- hydro_ts %>%
  model(STL(value ~ season(window = 5))) #window is your window for the moving average


components(dcmp) %>% autoplot() #this will plot your decomposed time series data

hist(components(dcmp)$remainder) # looks normal!

Now look at ACF:

hydro_ts %>% 
  ACF(value) %>% 
  autoplot()

#looking at this autoplot, we can see that observations that are 12 months apart are more highly correlated than any other observations any other distance apart

DANGER DANGER

hydro_model <- hydro_ts %>% 
  model(
    ARIMA(value),
      ETS(value)
  ) %>% 
  fabletools::forecast(h = "4 years")


hydro_model %>% autoplot(filter(hydro_ts, year(month_sep) > 2010)) #take the year part of month_sep

Make a world map!

world <- read_sf(dsn = here("data", "TM_WORLD_BORDERS_SIMPL-0.3-1"),
                 layer = "TM_WORLD_BORDERS_SIMPL-0.3")

mapview(world)